Browsing by Author "Rajpurohit, N.S."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Microwave assisted catalytic co-pyrolysis of banana peels and polypropylene: experimentation and machine learning optimization
    (Royal Society of Chemistry, 2025) Rajpurohit, N.S.; Sinha, S.; Ramesh, R.; Sankar Rao, C.; Harshini, H.
    The growing accumulation of agricultural and plastic waste poses serious environmental challenges, necessitating sustainable and efficient valorization strategies. This study investigates the microwave-assisted catalytic co-pyrolysis of banana peels and polypropylene, using graphite as a susceptor and potassium hydroxide as a catalyst. Experiments were conducted by varying biomass and plastic quantities and microwave power levels to study their effects on product yields and thermal performance. The process effectively converted waste materials into valuable products, with oil yield increasing with microwave power and optimized biomass-to-plastic ratios. The rate of mass loss and heating rate were found to significantly influence overall conversion efficiency. A support vector regression (SVR) model was developed to predict yields based on input parameters, achieving a coefficient of determination ranging from 0.81 to 0.99, which demonstrates the reliability of machine learning in capturing complex thermochemical behavior. 3D plots illustrated the nonlinear effects of process variables on yields. Fourier Transform Infrared Spectroscopy (FTIR) and X-ray Diffraction (XRD) analyses of char confirmed functional groups and crystalline phases, suggesting its suitability for applications like adsorbents or catalysts. Brunauer-Emmett-Teller (BET) analysis showed multilayer adsorption, while thermogravimetric analysis (TGA) highlighted distinct thermal degradation patterns of the feedstocks. These results affirm the promise of integrating experiments with ML for efficient waste-to-energy conversion. © 2025 The Royal Society of Chemistry.
  • No Thumbnail Available
    Item
    Predictive modeling of product yields in microwave-assisted co-pyrolysis of biomass and plastic with enhanced interpretability using explainable AI approaches
    (Elsevier B.V., 2025) Rajpurohit, N.S.; Kamani, P.K.; Lenka, M.; Sankar Rao, C.
    Microwave-assisted co-pyrolysis of biomass and plastic offers a transformative approach to converting waste into valuable resources such as bio-oil, biochar, and biogas, while simultaneously addressing critical environmental challenges associated with plastic disposal. This research employs explainable AI methodologies to enhance the prediction and analysis of product yields in biomass-plastic co-pyrolysis. Advanced machine learning techniques, including Decision Tree, Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks, were utilized to model yield predictions effectively. The models were fine-tuned through hyper-parameter optimization, achieving high accuracy levels. The study emphasizes the scientific importance of integrating explainable AI with pyrolysis processes to optimize waste-to-resource recovery, contributing significantly to sustainable waste management and circular economy initiatives. Among these, the XGBoost model demonstrated superior performance, achieving R² values of 0.91 for biochar yield, 0.92 for bio-oil yield, and 0.82 for biogas yield on testing sets. To enhance model interpretability, SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) were utilized to assess feature importance and examine parameter influences on yield outcomes, offering valuable insights into process optimization and control. Volatile matter and fixed carbon were key predictors for biochar yield, while moisture content and pyrolysis temperature were significant for predicting bio-oil and biogas yields. This study highlights the potential of explainable AI models in advancing sustainable and efficient bio-product recovery from waste materials. © 2025 Elsevier B.V.